Jiankai Zuo
Papers
6
Total Citations
33
H-Index
4
About
Jiankai Zuo is a researcher at the forefront of intelligent robotics and human-machine interaction, specializing in deep learning architectures for perceptual recognition and control systems. His work centers on developing advanced neural network models—particularly combinations of Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Gated Recurrent Units (GRUs)—to solve critical challenges in prosthetic control and autonomous robot navigation. Zuo’s most cited paper, “Intelligent Classification of Multi-Gesture EMG Signals Based on LSTM” (2020, 11 citations), demonstrates his impact on rehabilitation technology by enabling accurate decoding of human motion intentions from electromyographic signals for advanced prosthetic control. He has further contributed to mobile robotics through innovative ground classification methods, including a CNN-LSTM model that improves terrain recognition accuracy, and hybrid classifiers combining decision trees with random forests and LightGBM for robust environmental perception. His research addresses fundamental challenges in unstructured surface identification and robot drive form recognition, bridging the gap between deep learning theory and practical robotic systems. With a growing citation record and a focus on real-world applications from rehabilitation to autonomous navigation, Zuo’s work represents a significant step toward more intelligent, perceptive, and responsive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Intelligent Classification of Multi-Gesture EMG Signals Based on LSTM11 citations · 2020
- 2
- 3Robot Ground Classification and Recognition Based on CNN-LSTM Model7 citations · 2021
- 4
- 5
- 6